Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocols
    -0.07
     gays
    -0.07
    鼓
    -0.07
     budget
    -0.06
    .ignore
    -0.06
    ателей
    -0.06
    _TH
    -0.06
     while
    -0.06
    occasion
    -0.06
    _students
    -0.06
    POSITIVE LOGITS
    }]
    0.07
     gather
    0.07
     Tahoe
    0.06
     ]).
    0.06
    ");}↵
    0.06
    <System
    0.06
    olk
    0.06
    _locals
    0.05
     βο
    0.05
    ()!=
    0.05
    Act Density 0.075%

    No Known Activations